发表机构
Institute for Cybernetics of NAS of Ukraine（乌克兰国家科学院控制论研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对LLM智能体规划计算成本高和行为随机的问题，提出GATS框架，结合系统树搜索与分层世界模型，在合成任务和综合测试中表现优异，规划时无需LLM调用，生成确定性计划，优于LLM引导探索。
AI 中文摘要
大语言模型（LLM）智能体在多步规划任务中展现出潜力，但现有方法如LATS和ReAct在规划时严重依赖LLM推理，导致高计算成本和随机行为。我们提出GATS（图增强树搜索），一种将基于UCB1的系统树搜索与分层世界模型相结合的规划框架，在推理时消除LLM调用，同时实现卓越规划性能。我们的三层世界模型整合了精确符号动作匹配、从执行日志学习的统计信息以及基于LLM的未知动作预测。在具有分支路径和死胡同的合成规划任务中，GATS成功率达100%，而LATS为92%，ReAct为64%。在涵盖12个具有挑战性场景的综合压力测试中，GATS保持100%成功率，而LATS降至88.9%，ReAct降至23.9%。GATS在规划时每个任务无需LLM调用（LATS为每个任务37次），且生成的确定性计划跨运行无方差。我们的结果表明，基于学习的世界模型的系统搜索在智能体规划方面可显著优于LLM引导的探索。
英文摘要
Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during inference while achieving superior planning performance. Our three-layer world model integrates: (L1) exact symbolic action matching, (L2) statistics learned from execution logs, and (L3) LLM-based prediction for unknown actions. On synthetic planning tasks with branching paths and dead-ends, GATS achieves \textbf{100\% success rate} compared to 92 % for LATS and 64\% for ReAct. On a comprehensive stress test spanning 12 challenging scenarios -- including coding workflows, web navigation, and long-horizon tasks -- GATS maintains \textbf{100\% success} while LATS drops to 88.9 % and ReAct to 23.9%. GATS requires \textbf{zero LLM calls per task} during planning (vs. 37 per task for LATS) and produces deterministic plans with zero variance across runs. Our results demonstrate that systematic search with learned world models can substantially outperform LLM-guided exploration for agent planning.
